Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54147
    Prev
    Next
    INDEX
    Explanations

    quotient

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intensified
    -0.08
    ssc
    -0.08
    edies
    -0.08
     Katherine
    -0.08
     Overs
    -0.07
    Differ
    -0.07
     portée
    -0.07
     händer
    -0.07
    산
    -0.07
     dread
    -0.07
    POSITIVE LOGITS
    和值
    0.08
    是多少
    0.08
    	FILE
    0.08
     obtenido
    0.08
    Chap
    0.08
     Dynasty
    0.07
     👍
    0.07
     kısm
    0.07
    月份
    0.07
    、副
    0.07
    Activations Density 0.005%

    No Known Activations